saarika:v2.5
Speech-to-Text
Accurate transcription built for Indian accents, dialects, and real-world audio with speaker diarisation.
sarvam-m
LLM
Multilingual large language model with native proficiency across Indian languages for text generation and reasoning.
1.
Install Pipecat
pip install pipecat-ai[sarvam]
2.
Add Sarvam API key
Set SARVAM_API_KEY in your environment
3.
Build your pipeline
Use SarvamSTTService() and SarvamLLMService() in your pipeline
python
# Install
pip install pipecat-ai[sarvam]
# In your pipeline
from pipecat.services.sarvam import SarvamSTTService
from pipecat.services.sarvam import SarvamLLMService
stt = SarvamSTTService(api_key=os.getenv("SARVAM_API_KEY"))
llm = SarvamLLMService(api_key=os.getenv("SARVAM_API_KEY"))
pipeline = Pipeline([transport.input(), stt, llm, tts, transport.output()])IVR
IVR & Call Centres
Build conversational IVR systems with Indic-language understanding.
Voice
Voice Assistants
Create multimodal voice assistants with real-time streaming.
Rapid
Rapid Prototyping
Go from idea to working voice agent in under an hour.
Type Open Source
Language Python
Maintained by Daily.co
Install pip install pipecat-ai[sarvam]
Ready to build? Start building with Pipecat in minutes.
Ready to build?
Start building with Pipecat in minutes.